CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

TL;DR

CoMo introduces a novel unsupervised learning framework that captures continuous latent motion from internet videos, improving robot learning by focusing on foreground dynamics and enabling zero-shot generalization.

Contribution

It proposes the CoMo method with temporal difference and contrastive learning to better capture continuous motion and enhance zero-shot policy transfer in robot learning.

Findings

CoMo achieves superior motion representation quality.

Policies trained with CoMo pseudo labels outperform baselines.

Strong zero-shot generalization demonstrated on unseen videos.

Abstract

Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting excessive static backgrounds through vector quantization with a small codebook size. However, they suffer from information loss and struggle to capture more complex and fine-grained dynamics. Moreover, there is an inherent gap between the distribution of discrete latent motion and continuous robot action, which hinders the joint learning of a unified policy. We propose CoMo, which aims to learn more precise continuous latent motion from internet-scale videos. CoMo employs an early temporal difference (Td) mechanism to increase the shortcut learning difficulty and explicitly enhance motion cues. Additionally, to ensure latent motion better captures meaningful foregrounds, we further propose a temporal contrastive learning (Tcl) scheme. Specifically, positive pairs are constructed with a small future frame temporal offset, while negative pairs are formed by directly reversing the temporal direction. The proposed Td and Tcl work synergistically and effectively ensure that the latent motion focuses better on the foreground and reinforces motion cues. Critically, CoMo exhibits strong zeroshot generalization, enabling it to generate effective pseudo action labels for unseen videos. Extensive simulated and real-world experiments show that policies co-trained with CoMo pseudo action labels achieve superior performance with both diffusion and auto-regressive architectures.